// Analyze a PRD for edge cases, failure modes, and scenarios that might be missed. Use after creating a PRD to strengthen it. Triggers on: analyze edge cases, find edge cases, what could go wrong, edge case analysis.
| name | edge-cases |
| description | Analyze a PRD for edge cases, failure modes, and scenarios that might be missed. Use after creating a PRD to strengthen it. Triggers on: analyze edge cases, find edge cases, what could go wrong, edge case analysis. |
Systematically analyze a PRD to identify edge cases, failure modes, race conditions, and scenarios that might be overlooked during implementation.
Output: A list of edge cases with recommended PRD updates.
For each user story in the PRD:
Understand what the story is trying to accomplish.
Go through each edge case category above and ask:
For each identified edge case:
For each edge case, propose one of:
# Edge Case Analysis for [PRD Name]
## Summary
- Total edge cases identified: X
- Critical: X | High: X | Medium: X | Low: X
## Edge Cases by Story
### US-001: [Story Title]
| Edge Case | Category | Severity | Recommended Action |
|-----------|----------|----------|-------------------|
| User submits empty form | Input | High | Add acceptance criteria: "Empty form shows validation errors" |
| User double-clicks submit | User Behavior | Medium | Add acceptance criteria: "Submit button disabled after first click" |
### US-002: [Story Title]
...
## New Stories Recommended
### US-NEW-001: Handle concurrent edits
**Description:** As a user, I want to see a warning if someone else has edited the item since I started editing.
**Acceptance Criteria:**
- [ ] System checks for updates before saving
- [ ] Warning shown if data has changed
- [ ] User can choose to overwrite or refresh
**Rationale:** Addresses race condition edge case in US-003 and US-004.
## Updated Functional Requirements
- FR-NEW-1: The system must validate all user input on both client and server side
- FR-NEW-2: All destructive operations must be idempotent
## Technical Considerations to Add
- Implement optimistic locking for concurrent edit detection
- Add retry logic with exponential backoff for network failures
- Use database transactions for multi-step operations
Convert bug reports into prd.json user stories for autonomous fixing. Use after running test-and-break skill. Triggers on: convert bugs to stories, fix these bugs, add bugs to prd, create fix stories.
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification. Use when: (1) Creating threat models programmatically using Python code, (2) Generating data flow diagrams (DFDs) with automatic STRIDE threat identification, (3) Integrating threat modeling into CI/CD pipelines and shift-left security practices, (4) Analyzing system architecture for security threats across trust boundaries, (5) Producing threat reports with STRIDE categories and mitigation recommendations, (6) Maintaining threat models as code for version control and automation.
Hardcoded secret detection and prevention in git repositories and codebases using Gitleaks. Identifies passwords, API keys, tokens, and credentials through regex-based pattern matching and entropy analysis. Use when: (1) Scanning repositories for exposed secrets and credentials, (2) Implementing pre-commit hooks to prevent secret leakage, (3) Integrating secret detection into CI/CD pipelines, (4) Auditing codebases for compliance violations (PCI-DSS, SOC2, GDPR), (5) Establishing baseline secret detection and tracking new exposures, (6) Remediating historical secret exposures in git history.
Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports. Use after deploying to staging. Triggers on: test the app, find bugs, QA the deployment, break the app, test staging.
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
Review user stories for quality, proper sizing, sequencing, and acceptance criteria. Use before converting to prd.json. Triggers on: review stories, check user stories, story quality, validate stories.